David Belton

Robust Segmentation in Laser Scanning 3D Point Cloud Data

Segmentation is a most important intermediate step in point cloud data processing and understanding. Covariance statistics based local saliency features from Principal Component Analysis (PCA) are frequently used for point cloud segmentation. However it is well known that PCA is sensitive to outliers. Hence segmentation results can be erroneous and unreliable. The problems of surface segmentation in laser scanning point cloud data are investigated in this paper. We propose a region growing based statistically robust segmentation algorithm that uses a recently introduced fast Minimum Covariance Determinant (MCD) based robust PCA approach. Experiments for several real laser scanning datasets show that PCA gives unreliable and non-robust results whereas the proposed robust PCA based method has intrinsic ability to deal with noisy data and gives more accurate and robust results for planar and non planar smooth surface segmentation.

A Closed-Form Expression of the Positional Uncertainty for 3D Point Clouds

We present a novel closed-form expression of positional uncertainty measured by a near-monostatic and time-of-flight laser range finder with consideration of its measurement uncertainties. An explicit form of the angular variance of the estimated surface normal vector is also derived. This expression is useful for the precise estimation of the surface normal vector and the outlier detection for finding correspondence in order to register multiple three-dimensional point clouds. Two practical algorithms using these expressions are presented: a method for finding optimal local neighbourhood size which minimizes the variance of the estimated normal vector and a resampling method of point clouds.

Robust Segmentation for Large Volumes of Laser Scanning Three-Dimensional Point Cloud Data

This paper investigates the problems of outliers and/or noise in surface segmentation and proposes a statistically robust segmentation algorithm for laser scanning 3-D point cloud data. Principal component analysis (PCA)-based local saliency features, e.g., normal and curvature, have been frequently used in many ways for point cloud segmentation. However, PCA is sensitive to outliers; saliency features from PCA are nonrobust and inaccurate in the presence of outliers; consequently, segmentation results can be erroneous and unreliable. As a remedy, robust techniques, e.g., RANdom SAmple Consensus (RANSAC), and/or robust versions of PCA (RPCA) have been proposed. However, RANSAC is influenced by the well-known swamping effect, and RPCA methods are computationally intensive for point cloud processing. We propose a region growing based robust segmentation algorithm that uses a recently introduced maximum consistency with minimum distance based robust diagnostic PCA (RDPCA) approach to get robust saliency features. Experiments using synthetic and laser scanning data sets show that the RDPCA-based method has an intrinsic ability to deal with outlier- and/or noise-contaminated data. Results for a synthetic data set show that RDPCA is 105 times faster than RPCA and gives more accurate and robust results when compared with other segmentation methods. Compared with RANSAC and RPCA based methods, RDPCA takes almost the same time as RANSAC, but RANSAC results are markedly worse than RPCA and RDPCA results. Coupled with a segment merging algorithm, the proposed method is efficient for huge volumes of point cloud data consisting of complex objects surfaces from mobile, terrestrial, and aerial laser scanning systems.

Robust Locally Weighted Regression Techniques for Ground Surface Points Filtering in Mobile Laser Scanning Three Dimensional Point Cloud Data

This paper introduces robust algorithms for extracting the ground points in laser scanning 3-D point cloud data. Global polynomial functions have been used for filtering algorithms for point cloud data; however, it is not suitable as it may lead to bias for the filtering algorithms and can cause misclassification errors when many different objects are present. In this paper, robust statistical approaches are coupled with locally weighted 2-D regression that fits without any predefined global function for the variables of interest. Algorithms are performed iteratively on 2-D profiles: x - z and y - z. The z (elevation) values are robustly down weighted based on the residuals for the fitted points. The new set of down-weighted z values, along with the corresponding x (or y) values, is used to get a new fit for the lower surface level. The process of fitting and down weighting continues until the difference between two consecutive fits is insignificant. The final fit is the required ground level, and the ground surface points are those that fall within the ground level and the level after adding some threshold value with the ground level for z values. Experimental results are compared with the recently proposed segmentation method through simulated and real mobile laser scanning point clouds from urban areas that include many objects that appear in road scenes such as short walls, large buildings, electric poles, signposts, and cars. Results show that the proposed robust methods efficiently extract ground surface points with better than 97% accuracy.

Pilbara rock art: Laser scanning, photogrammetry and 3D photographic reconstruction as heritage management tools

Recording techniques such as laser scanning, photogrammetry and photographic reconstruction are not new to archaeology. However as technology evolves and becomes more readily available such methods are being more regularly employed within a cultural heritage management context, often by people with little experience in using these technologies for heritage applications. For most cultural heritage management practitioners, the awe and lure of technology and the ease with which it can bring archaeology to life can distract from the end game of managing the site on the ground. This paper examines the advantages and disadvantages of laser scanning, photogrammetry and photographic reconstruction in recording, managing and interpreting rock art sites with an emphasis on its practical applications to the field of heritage management. Using a case study from West Angelas in the East Pilbara region of Western Australia, we will examine how these technologies assist in the practical management of heritage sites, and the significant outputs achieved for Aboriginal stakeholder groups in remote access to, and the interpretation of indigenous heritage sites.

Semantically enhanced 3D building model reconstruction from terrestrial laser-scanning data

AbstractIn recent years, three-dimensional (3D) models have been used in a large variety of applications, and the steadily growing capacity in both quality and quantity is increasing demand. To app...

Automatic Point Cloud Registration Using a Single Octagonal Lamp Pole

Abstract Registration is an essential procedure for merging point clouds defined in different coordinate systems associated to different scanner positions and orientations. It is usually the first step before the point clouds are further processed to provide spatial information of a scene to support engineering applications. In this paper, a new automatic registration method based on a novel geometric model of a polygonal object is presented. Since the cross section of the shaft of many lamp poles is octagonal, registration based on an octagonal pyramid model is proposed. The presented method only requires a single, common octagonal lamp pole observed in both point clouds, though actual overlap of the point clouds is not strictly required. It can be performed as long as the model parameters can be estimated by fitting the point observations to the model. Moreover, no user interaction is needed to derive approximate values, so the proposed registration can be completely automated. Three independent datasets captured by two scanners were used to verify the method. The registration accuracies in the horizontal and vertical directions were up to 11.7 mm and 4.4 mm at approximately 62 m and 17 m away from the scanner, respectively. With such high accuracies, the estimated registration parameters can serve as a set of initial parameters for fine registration using algorithm such as the iterative closest point ( icp ).

Non-parametric belief propagation for mobile mapping sensor fusion

Abstract Many different forms of sensor fusion have been proposed each with its own niche. We propose a method of fusing multiple different sensor types. Our approach is built on the discrete belief propagation to fuse photogrammetry with GPS to generate three-dimensional (3D) point clouds. We propose using a non-parametric belief propagation similar to Sudderth et al’s work to fuse different sensors. This technique allows continuous variables to be used, is trivially parallel making it suitable for modern many-core processors, and easily accommodates varying types and combinations of sensors. By defining the relationships between common sensors, a graph containing sensor readings can be automatically generated from sensor data without knowing a priori the availability or reliability of the sensors. This allows the use of unreliable sensors which firstly, may start and stop providing data at any time and secondly, the integration of new sensor types simply by defining their relationship with existing sensors. These features allow a flexible framework to be developed which is suitable for many tasks. Using an abstract algorithm, we can instead focus on the relationships between sensors. Where possible we use the existing relationships between sensors rather than developing new ones. These relationships are used in a belief propagation algorithm to calculate the marginal probabilities of the network. In this paper, we present the initial results from this technique and the intended course for future work.

MLS-assisted validation of WorldView-2 panchromatic image for estimating Pinus sylvestris crown height

High spatial resolution satellite imaging has the advantages of both fine scale and large coverage that indicate the potential for measuring forest morphologies. However, because of the aerial view, imaging has limited capacity of explicitly deriving the under-crown structural parameters. A possible solution is to explore the relationships between this kind of variables such as crown height (CH) and the feature parameters readily derived from the satellite images. However, field sampling of the training data is not a trivial task. To handle this issue, this study attempted the state-of-the-art remote sensing technology of vehicle-based mobile laser scanning (MLS) for collecting the sample data. Evaluation for the case of the Scots pine (Pinus sylvestris) trees has preliminarily validated the plan. That is, MLS mapping enabled the parameter of CH to be estimated from WorldView-2 panchromatic images.